import os
import numpy as np
import pandas as pd
import cv2
import matplotlib.pylab as plt

from plotly.subplots import make_subplots
import plotly.graph_objects as go
import plotly.express as px
import matplotlib.pylab as plt
from IPython.display import display, clear_output
from ipywidgets import interact, widgets

csv_path = "CodingChallenge_v2/car_imgs_4000.csv"
images_folder = "CodingChallenge_v2/imgs"

df = pd.read_csv(csv_path)
df.head()

	filename	perspective_score_hood	perspective_score_backdoor_left
0	66ee2d88-f403-4821-a370-8a3d72e200f9.jpg	0.27352	0.439526
1	bf7e237e-f12b-4ffc-8d79-6855cc35ea06.jpg	0.00000	0.902682
2	4c297488-c81f-464d-92bf-1c408333a912.jpg	0.00000	0.900864
3	6c95ad0b-fda6-42a8-a33d-b430073e1dcd.jpg	0.00000	0.213162
4	bd806d94-4c2e-4cd2-8e02-5eaba7c7c63e.jpg	0.00000	0.818388

df.shape

(4000, 3)

df[df.perspective_score_hood > 0].shape

(1897, 3)

df.perspective_score_hood.mean(), df.perspective_score_backdoor_left.mean()

(0.30303198100175, 0.31336786319750004)

This does not seem as a great imbalance, at least at first glance

fig = make_subplots(rows=1, cols=2)
fig.add_trace(go.Histogram(
    x=df.perspective_score_hood, name="perspective_score_hood"), row=1, col=1)
fig.add_trace(go.Histogram(
    x=df.perspective_score_backdoor_left, name="perspective_score_backdoor_left"), row=1, col=2)

Even scores have similar distribution, interesting

images = df.filename.to_list()
hood_scores = df.perspective_score_hood.to_list()
backdoor_scores = df.perspective_score_backdoor_left.to_list()

slider = widgets.IntSlider(
    value=0,
    min=0,
    max=len(images)-1)

@interact(file=slider)
def plot_file(file):
    img_path = f"{images_folder}/{images[file]}"
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    fig = plt.imshow(img)
    plt.title(f"hood score: {hood_scores[file]}, backdoor score: {backdoor_scores[file]}")

There are quiet a lot of the images which are indeed a mixture of classes, also there are pictures which have none of the classes. This should also contribute to better generalization.

slider = widgets.IntSlider(
    value=3709,
    min=0,
    max=len(images)-1)

@interact(file=slider)
def plot_file(file):
    img_path = f"{images_folder}/{images[file]}"
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    fig = plt.imshow(img)
    plt.title(f"hood score: {hood_scores[file]}, backdoor score: {backdoor_scores[file]}")

I have my doubts as for some pictures, where I would say scores are off. I will use them in the following training anyway, but my yellow flag would go after a discussion. For example, the following picture seem to contain left bakdoor while both scores are 0. I would have no problem with that, if the task would clearly state, that we need score more than 0 only for objects which fully get into the image

slider = widgets.IntSlider(
    value=3289,
    min=0,
    max=len(images)-1)

@interact(file=slider)
def plot_file(file):
    img_path = f"{images_folder}/{images[file]}"
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    fig = plt.imshow(img)
    plt.title(f"hood score: {hood_scores[file]}, backdoor score: {backdoor_scores[file]}")

I will get down to the main business and come back, if I have more time